PythonAnywhere MCP Server

What is PythonAnywhere MCP Server about?

PythonAnywhere MCP Server enables AI‑driven tools to interact securely with a PythonAnywhere account. By exposing a standardized MCP interface, it allows language models and automation clients to read, write, and delete files, manage ASGI/WSGI web applications, and control scheduled tasks.

How to use PythonAnywhere MCP Server?

Install uv (or ensure it is available in your PATH).
Obtain your PythonAnywhere API token and username from the account’s API section.
Run the server using uvx:
```
uvx pythonanywhere-mcp-server
```
Configure the client (Claude Desktop, GitHub Copilot, Cursor, etc.) by adding an MCP entry that points to the running server and supplies the required environment variables (API_TOKEN and PYTHONANYWHERE_USERNAME).

Key Features of PythonAnywhere MCP Server

File management – read, upload, delete, and list directory trees.
ASGI web app management – create, delete, reload, and list applications.
WSGI web app management – reload existing applications.
Scheduled task management – list, create, update, and delete tasks.
Fine‑grained auditability – all actions are routed through a controlled protocol.

Use Cases of PythonAnywhere MCP Server

Automated deployment – let an LLM generate code, upload files, and restart a web app without manual steps.
Continuous debugging – AI agents read log files directly to diagnose issues.
Scheduled job orchestration – create or modify cron‑style tasks from within a conversational interface.
Educational tooling – students can experiment with live PythonAnywhere environments via chat‑based assistants.

FAQ

Q: Do I need to expose my API token to the AI model? A: The token is passed as an environment variable to the MCP server, which runs locally. The AI client never sees the raw token.

Q: Can I run multiple MCP servers at the same time? A: Yes, but be cautious about overlapping capabilities and external resource access, as it may introduce attack vectors.

Q: What happens if a scheduled task is created with a near‑future execution time? A: The task could execute arbitrary commands. It is recommended to pair the server with mcp-server-time to avoid time‑related confusion.

Q: Is the server compatible with non‑Claude clients? A: Absolutely. Any client that implements the MCP specification (e.g., GitHub Copilot, Cursor) can connect by providing the appropriate configuration.

Q: How do I set the site for EU accounts? A: Export PYTHONANYWHERE_SITE=eu.pythonanywhere.com before starting the server.

PythonAnywhere Model Context Protocol Server

A Model Context Protocol (MCP) server acts as a bridge between AI-powered tools and your PythonAnywhere account, enabling secure, programmatic management of files, websites, webapps, and scheduled tasks. By exposing a standardized interface, it allows language models and automation clients to perform operations—such as editing files, deploying web apps, or scheduling jobs -- on your behalf, all while maintaining fine-grained control and auditability.

Features

File management: Read, upload, delete files and list directory trees. (also enables debugging with direct access to log files, which are just files on PythonAnywhere)
ASGI Web app management: Create, delete, reload, and list. (as described in the PythonAnywhere ASGI documentation)
WSGI Web app management: Reload only (at the moment).
Scheduled task management: List, create, update, and delete. (Note that this enables LLMs to execute arbitrary commands if a task is scheduled too soon after creation and deleted after execution. For that we would suggest running it with mcp-server-time as models easily get confused about time.)

Installation

The MCP protocol is well-defined and supported by various clients, but installation is different depending on the client you are using. We will cover cases that we tried and tested.

In all cases, you need to have uv installed and available in your PATH.

Have your PythonAnywhere API token and username ready. You can find (or generate) your API token in the API section of your PythonAnywhere account.

If your account is on eu.pythonanywhere.com, you also need to set PYTHONANYWHERE_SITE to eu.pythonanywhere.com (it defaults to www.pythonanywhere.com).

MCP Bundle - works with Claude Desktop

Probably the most straightforward way to install the MCP server is to use the MCP Bundle for Claude Desktop.

Open Claude Desktop.
Download the latest .mcpb file.
Double-click on the downloaded .dxt file or drag the file into the window.
Configure your PythonAnywhere API token and username.
Restart Claude Desktop.

Claude Code

Run:

claude mcp add pythonanywhere-mcp-server \
-e API_TOKEN=yourpythonanywhereapitoken \
-e PYTHONANYWHERE_USERNAME=yourpythonanywhereusername \
-- uvx pythonanywhere-mcp-server

GitHub Copilot in PyCharm:

Add it to your mcp.json.

{
  "servers": {
    "pythonanywhere-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": ["pythonanywhere-mcp-server"],
      "env": {
        "API_TOKEN": "yourpythonanywhereapitoken",
        "PYTHONANYWHERE_USERNAME": "yourpythonanywhereusername"
      }
    }
  }
}

Claude Desktop (manual setup) and Cursor:

Add it to claude_desktop_config.json (for Claude Desktop) or (mcp.json for Cursor).

{
  "mcpServers": {
    "pythonanywhere-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": ["pythonanywhere-mcp-server"],
      "env": {
        "API_TOKEN": "yourpythonanywhereapitoken",
        "PYTHONANYWHERE_USERNAME": "yourpythonanywhereusername"
      }
    }
  }
}

Caveats

Direct integration of an LLM with your PythonAnywhere account offers significant capabilities, but also introduces risks. We strongly advise maintaining human oversight, especially for sensitive actions such as modifying or deleting files.

If you are running multiple MCP servers simultaneously, be cautious -- particularly if any server can access external resources you do not control, such as GitHub issues. These can become attack vectors. For more details, see this story.

Implementation

The server uses the python mcp sdk in connection with the pythonanywhere-core package (docs), which wraps a subset of the PythonAnywhere API and may be expanded in the future as needed.